An intelligent evaluation method and device for academic papers based on multidimensional vector representation

Abstract

The present application relates to the field of machine learning technology, and in particular to a method and device for intelligent evaluation of academic papers based on multidimensional vector representation, wherein multidimensional vectors are extracted from the academic paper to be evaluated; wherein the extracted multidimensional vectors include vocabulary vectors, part-of-speech vectors, and paragraph vectors; the extracted vocabulary vectors, the part-of-speech vectors, and the paragraph vectors are input into a trained deep neural network model for processing to obtain a preliminary evaluation result of the academic paper to be evaluated; the academic paper to be evaluated and the preliminary evaluation result are input into a comprehensive scoring model for processing to obtain a final evaluation result of the academic paper to be evaluated; wherein the comprehensive scoring model integrates a variety of machine learning algorithms. Thus, a multidimensional feature analysis is performed on the academic paper to be evaluated, making the evaluation more in-depth, and a comprehensive evaluation of the paper quality is performed in combination with a variety of machine learning algorithms, thereby improving the accuracy and efficiency of the evaluation.

Description

Technical Field

[0001] The present application relates to the field of machine learning technology, and in particular to a method and device for intelligent evaluation of academic papers based on multi-dimensional vector representation. Background Art

[0002] Traditional paper evaluation methods typically rely on keyword matching and grammar checking, which fail to deeply understand the content quality and logical structure of a paper. They often overlook the specific meaning and usage of words in context, resulting in inaccurate and incomplete evaluation results. With the explosive growth of information, the academic field is increasingly in need of efficient and accurate paper evaluation methods. Traditional manual evaluation methods are time-consuming and highly subjective, making them difficult to meet the needs of large-scale academic evaluation. Summary of the Invention

[0003] In order to overcome the deficiencies in the prior art, the present application provides an intelligent evaluation method and device for academic papers based on multi-dimensional vector representation, which can realize multi-dimensional semantic analysis and improve evaluation efficiency and accuracy.

[0004] In a first aspect, the present application provides an intelligent evaluation method for academic papers based on multidimensional vector representation, the method comprising the following steps:

[0005] Extract multidimensional vectors from the academic papers to be evaluated; the extracted multidimensional vectors include vocabulary vectors, part-of-speech vectors, and paragraph vectors;

[0006] Inputting the extracted vocabulary vector, the part-of-speech vector, and the paragraph vector into a trained deep neural network model for processing to obtain a preliminary evaluation result of the academic paper to be evaluated;

[0007] The academic paper to be evaluated and the preliminary evaluation result are input into a comprehensive scoring model for processing to obtain a final evaluation result of the academic paper to be evaluated; wherein the comprehensive scoring model integrates multiple machine learning algorithms.

[0008] In a possible implementation, extracting multidimensional vectors from the academic paper to be evaluated includes the following steps:

[0009] Preprocessing the academic papers to be evaluated; the preprocessing includes denoising, word segmentation, part-of-speech tagging, and paragraph segmentation;

[0010] Extract vocabulary vectors from the pre-processed academic papers to be evaluated based on the word vector model;

[0011] Process the vocabulary vector and part-of-speech tagging information based on the part-of-speech vector model to obtain the part-of-speech vector;

[0012] Based on the paragraph vector model, the vocabulary vector, part-of-speech vector and paragraph segmentation information are processed to obtain the paragraph vector.

[0013] In a possible implementation, the extracted multidimensional vector further includes document topic features, wherein the document topic features are obtained by processing the academic paper to be evaluated based on a latent Dirichlet allocation model.

[0014] In one possible implementation, the deep neural network model is a three-layer neural network model consisting of an input layer, a hidden layer, and an output layer, and is trained as follows, including the following steps:

[0015] Initialize the weights and biases of the deep neural network;

[0016] Perform forward propagation on the training data to obtain prediction results; wherein the training data is a collection of vocabulary vectors, part-of-speech vectors, and paragraph vectors obtained by performing multidimensional vector extraction on a large number of collected academic paper samples;

[0017] Calculate the loss value based on the predicted result and the corresponding true label;

[0018] The backpropagation algorithm is used to calculate the gradient of the loss value with respect to the weight and bias, and the weight and bias are adjusted based on the gradient value until the deep neural network converges or reaches a preset number of training rounds.

[0019] In one possible implementation, the multiple machine learning algorithms integrated into the comprehensive scoring model include an extreme gradient boosting algorithm, a term frequency-inverse document frequency algorithm, a text ranking algorithm, and a k-nearest neighbor algorithm.

[0020] In a possible implementation, inputting the academic paper to be evaluated and the preliminary evaluation result into a comprehensive scoring model for processing to obtain a final evaluation result of the academic paper to be evaluated includes the following steps:

[0021] Optimizing the preliminary evaluation result based on an extreme gradient boosting algorithm to obtain an optimized preliminary evaluation result;

[0022] Inputting the academic paper to be evaluated into a word frequency-inverse document frequency algorithm and a text ranking algorithm for processing to obtain supplementary information; wherein, the word importance is calculated based on the word frequency-inverse document frequency algorithm and the text structure is analyzed based on the text ranking algorithm, and the obtained word importance and text structure information are used as the supplementary information;

[0023] Calibrate the preliminary evaluation result based on a k-nearest neighbor algorithm to obtain a calibrated preliminary evaluation result;

[0024] According to preset rules, the optimized preliminary evaluation results, supplementary information, and calibrated preliminary evaluation results are comprehensively evaluated to obtain the final evaluation results of the academic paper to be evaluated.

[0025] In one possible implementation, calibrating the preliminary evaluation result based on the k-nearest neighbor algorithm to obtain a calibrated preliminary evaluation result includes the following steps:

[0026] Calculate the Euclidean distance between the academic paper to be evaluated and each academic paper in the dataset based on the k-nearest neighbor algorithm;

[0027] Select at least one academic paper with the closest Euclidean distance as the nearest neighbor academic paper;

[0028] The preliminary evaluation results are calibrated according to the scores of the nearest neighbor academic papers.

[0029] In a second aspect, the present application provides an intelligent evaluation device for academic papers based on multidimensional vector representation, the device comprising:

[0030] An extraction module is used to extract multidimensional vectors from the academic papers to be evaluated; the extracted multidimensional vectors include vocabulary vectors, part-of-speech vectors, and paragraph vectors;

[0031] A preliminary evaluation module is used to input the extracted vocabulary vectors, the part-of-speech vectors, and the paragraph vectors into a trained deep neural network model for processing to obtain a preliminary evaluation result of the academic paper to be evaluated;

[0032] The comprehensive evaluation module is used to input the academic paper to be evaluated and the preliminary evaluation result into a comprehensive scoring model for processing to obtain the final evaluation result of the academic paper to be evaluated; wherein, the comprehensive scoring model integrates multiple machine learning algorithms.

[0033] In a third aspect, the present application provides an electronic device comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps of the intelligent evaluation method for academic papers based on multidimensional vector representation as described in any one of the first aspects are performed.

[0034] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, executes the steps of the intelligent evaluation method for academic papers based on multidimensional vector representation as described in any one of the first aspects.

[0035] This embodiment provides an intelligent evaluation method and device for academic papers based on multidimensional vector representation, which extracts multidimensional vectors from the academic papers to be evaluated; wherein the extracted multidimensional vectors include vocabulary vectors, part-of-speech vectors, and paragraph vectors; the extracted vocabulary vectors, part-of-speech vectors, and paragraph vectors are input into a trained deep neural network model for processing to obtain a preliminary evaluation result of the academic paper to be evaluated; the academic paper to be evaluated and the preliminary evaluation result are input into a comprehensive scoring model for processing to obtain a final evaluation result of the academic paper to be evaluated; wherein the comprehensive scoring model integrates multiple machine learning algorithms. Thus, a multidimensional feature analysis of the academic paper to be evaluated is performed, making the evaluation more in-depth, and a comprehensive evaluation of the paper quality is performed by combining multiple machine learning algorithms, thereby improving the accuracy and efficiency of the evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0037] Figure 1 A flowchart of an intelligent evaluation method for academic papers based on multidimensional vector representation according to an embodiment of the present application is shown;

[0038] Figure 2 A flowchart of extracting multidimensional vectors from an academic paper to be evaluated according to an embodiment of the present application is shown;

[0039] Figure 3 A flowchart of an embodiment of the present application is shown, in which the academic paper to be evaluated and the preliminary evaluation result are input into a comprehensive scoring model for processing to obtain a final evaluation result of the academic paper to be evaluated;

[0040] Figure 4 A schematic diagram of the structure of an intelligent evaluation device for academic papers based on multidimensional vector representation according to an embodiment of the present application is shown;

[0041] Figure 5 A structural block diagram of an electronic device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of illustration and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowcharts can be implemented out of sequence, and steps without logical context can be reversed or implemented simultaneously. In addition, those skilled in the art, under the guidance of the contents of this application, can add one or more other operations to the flowchart, or remove one or more operations from the flowchart.

[0043] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present application.

[0044] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

[0045] In view of the technical problems raised by the background technology, the present application provides an intelligent evaluation method and device for academic papers based on multi-dimensional vector representation, which can realize multi-dimensional semantic analysis and improve evaluation efficiency and accuracy.

[0046] In one embodiment, see the attached Figure 1 , this application provides an intelligent evaluation method for academic papers based on multidimensional vector representation, the method comprising the following steps:

[0047] S1. Extract multidimensional vectors from the academic papers to be evaluated. The extracted multidimensional vectors include vocabulary vectors, part-of-speech vectors, and paragraph vectors.

[0048] S2. Inputting the extracted vocabulary vector, the part-of-speech vector, and the paragraph vector into a trained deep neural network model for processing to obtain a preliminary evaluation result of the academic paper to be evaluated;

[0049] S3. Input the academic paper to be evaluated and the preliminary evaluation result into a comprehensive scoring model for processing to obtain a final evaluation result of the academic paper to be evaluated; wherein the comprehensive scoring model integrates multiple machine learning algorithms.

[0050] Specifically, in step S1, this application utilizes word2vec, pos2ve and paragraph2vec technologies, not only based on single keyword or grammatical analysis, but also captures the complex semantic features of words, sentences and paragraphs in the academic paper to be evaluated, making the subsequent evaluation process more in-depth and comprehensive, and able to accurately evaluate the content quality and logical structure of the academic paper to be evaluated.

[0051] See the instructions attached Figure 2 The multi-dimensional vector extraction of the academic paper to be evaluated includes the following steps:

[0052] S101. Preprocessing the academic paper to be evaluated; the preprocessing includes denoising, word segmentation, part-of-speech tagging, and paragraph segmentation;

[0053] S102. Extracting vocabulary vectors from the pre-processed academic papers to be evaluated based on the word vector model;

[0054] S103, processing the vocabulary vector and the part-of-speech tag information based on the part-of-speech vector model to obtain a part-of-speech vector;

[0055] S104: Process the vocabulary vector, part-of-speech vector, and paragraph segmentation information based on the paragraph vector model to obtain a paragraph vector.

[0056] In step S101, the academic paper to be evaluated is preprocessed mainly to improve data quality without affecting the accuracy of subsequent extraction of multidimensional vectors. The preprocessing methods include denoising, word segmentation, part-of-speech tagging and paragraph segmentation. Among them, denoising is mainly used for data cleaning, such as removing obvious format errors, garbled characters, special symbols, etc. in the academic paper to be evaluated. Word segmentation can use professional word segmentation tools, such as NLTK (Natural Language Toolkit), to divide continuous text into individual words. Part-of-speech tagging can use part-of-speech tagging tools, such as Stanford CoreNLP, spaCy, etc., to mark corresponding part-of-speech tags for each word according to the grammatical function and semantic features of the word in the sentence, such as noun, verb, adjective, adverb, etc. At the same time, paragraph segmentation is also performed based on punctuation or text structure features, and paragraph ID is marked to provide a good foundation for subsequent extraction of paragraph vectors.

[0057] In steps S102-S104, vocabulary vector is the basic structure of text, and a good vocabulary vector can make semantically similar words gather together, which helps subsequent operations such as text classification and text clustering. Therefore, in step S102, word vector model (word2vec) is used to extract vocabulary vector to the pre-processed academic paper to be evaluated. In the paper evaluation, part-of-speech vector can help judge the rationality of vocabulary collocation and the correctness of sentence structure. Therefore, in step S103, pos2vec model part-of-speech vector model (pos2vec) is used to map each part of speech to a low-dimensional vector. In this way, the word sequence in the sentence is converted into a part-of-speech vector sequence, and the vocabulary in the sentence is represented by vector from the part-of-speech angle. In the paper evaluation, paragraph vector can be used to analyze the paragraph coherence, theme consistency and the logical relationship between paragraphs of the paper. Therefore, in step S104, paragraph vector model (paragraph2vec) is used to process vocabulary vector, part-of-speech vector and paragraph segmentation information to obtain paragraph vector. The working principles of the word2vec model, pos2vec model, and paragraph2vec model are well known to those skilled in the art and will not be elaborated here.

[0058] It should be noted that before using the word2vec, pos2vec, and paragraph2vec models to extract multidimensional vectors from preprocessed academic papers to be evaluated, the word2vec, pos2vec, and paragraph2vec models need to be trained. For example, a dataset of student mock exam papers can be used as training data. After preprocessing, this data is input into the word2vec model for training. During the training process, the parameters of the vocabulary vectors are continuously adjusted to bring semantically similar words closer together in the vector space. After training, each word can be mapped to a fixed-length vector that contains the word's semantic information, providing a foundation for subsequent text analysis. Similar to the word2vec model, by training the pos2vec model, a vector representation of each part of speech is obtained. By training the paragraph2vec model, a vector representation of each paragraph is obtained.

[0059] Furthermore, the Latent Dirichlet Allocation (LDA) model can be used to extract the document topic features of the academic paper being evaluated. This is because the aforementioned word2vec, pos2vec, and paragraph2vec models primarily focus on local and mid-level semantic features of the text, while the LDA model focuses on revealing the thematic structure of the text at a global level. It can discover latent topics in a document collection and the distribution of each document across different topics. Combining word vectors, part-of-speech vectors, and paragraph vectors with document topic features can provide a richer and more comprehensive basis for subsequent evaluation.

[0060] In step S2, the extracted multidimensional vectors are used as the input of the deep neural network model. Through the weight connections and activation functions between neurons in each layer, these complex features are deeply analyzed and processed to capture the deep patterns and relationships in the academic papers to be evaluated, and then output the preliminary evaluation results of the quality of the academic papers to be evaluated.

[0061] In one embodiment, a three-layer neural network model (NNM) is used as the deep neural network model, consisting of an input layer, a hidden layer, and an output layer. Each layer is connected to each other via modifiable weights, and hidden layer units form a net activation through the weighted summation of their inputs. This architecture can effectively capture complex features and patterns in papers and understand the quality and logical structure of the paper's content. The deep neural network model is trained as follows: first, the weights and biases of the deep neural network are initialized, for example, using small random numbers. Then, the training data is forward propagated, and the data is weighted and summed in the hidden layer through the weighted connections to obtain a net activation value. This is then processed through an activation function to introduce nonlinearity into the model, enhancing the model's ability to learn complex relationships. The processed results are then passed to the next layer until the output layer obtains the predicted results. The predicted results of the deep neural network are then compared with the true labels of the paper samples in the training set (such as the actual score and quality level of the paper). An appropriate loss function is selected to calculate the difference between the two and obtain a loss value. Based on the calculated loss value, a backpropagation algorithm is used to calculate the gradient of the loss value with respect to the weights and biases. Based on the calculated gradient values, the optimization algorithm is used to update the weights and biases. This process of forward propagation, loss calculation, backpropagation, and parameter update is repeated until the deep neural network converges or reaches a preset number of training rounds.

[0062] In step S3, the preliminary evaluation results output by the deep neural network model are mainly used as one of the inputs of a comprehensive scoring model that integrates multiple machine learning algorithms to evaluate the academic papers from different perspectives and generate the final evaluation results.

[0063] In this application, the comprehensive scoring model integrates multiple machine learning algorithms including the extreme gradient boosting algorithm (eXtreme Gradient Boosting, XGBoost), the term frequency-inverse document frequency algorithm (Term Frequency-Inverse Document Frequency, TF-IDF), the text ranking algorithm (TextRank) and the k-nearest neighbor algorithm (kNN). Figure 3 The step of inputting the academic paper to be evaluated and the preliminary evaluation result into a comprehensive scoring model for processing to obtain the final evaluation result of the academic paper to be evaluated comprises the following steps:

[0064] S301, optimizing the preliminary evaluation result based on XGBoost to obtain an optimized preliminary evaluation result;

[0065] S302: Input the academic paper to be evaluated into TF-IDF and TextRank for processing to obtain supplementary information; wherein, the word importance is calculated based on TF-IDF and the text structure is analyzed based on TextRank, and the obtained word importance and text structure information are used as the supplementary information;

[0066] S303, calibrating the preliminary evaluation result based on kNN to obtain a calibrated preliminary evaluation result;

[0067] S304: Perform a comprehensive evaluation on the optimized preliminary evaluation results, the supplementary information, and the calibrated preliminary evaluation results according to preset rules to obtain a final evaluation result of the academic paper to be evaluated.

[0068] In step S301, XGBoost is a powerful gradient boosting framework. In this application, it optimizes the preliminary evaluation results output by the deep neural network model. Specifically, an objective function including a loss function and a regularization term is defined. The loss function can use the mean square error (MSE) to measure the difference between the preliminary evaluation result and the true score, and the regularization term prevents the model from overfitting. XGBoost uses an iterative method to construct a decision tree. Each round of iterative fitting of a new tree predicts the residual of the previous round, and continuously reduces the loss function value. When constructing a decision tree, a greedy algorithm is used to traverse the features and split values, and the split point with the largest gain is selected for splitting. After the tree is built, a pruning operation is performed to remove leaf nodes that do not significantly improve the performance of the model, thereby optimizing the preliminary evaluation results.

[0069] In step S302, supplementary information is mainly provided by TF-IDF and TextRank. Among them, TF-IDF is used to calculate the importance of vocabulary, and TextRank is used to analyze the text structure. Specifically, TF-IDF first calculates the word frequency (TF) to indicate the frequency of a word appearing in the paper, and then calculates the inverse document frequency (IDF) to measure the general importance of a word. The word frequency (TF) and the inverse document frequency (IDF) are then multiplied to obtain the TF-IDF value of each word in the academic paper to be evaluated, and the TF-IDF value is used to reflect the importance of vocabulary. TextRank constructs a graph model, takes the sentences or words in the academic paper to be evaluated as nodes, and uses methods such as cosine similarity to calculate the similarity between nodes to determine the edges. An iterative algorithm (such as PageRank) is used to calculate the node weights. Sentences with high weights are key sentences, reflecting the logical structure and core ideas of the paper. Words with high weights are used as keywords, which complement TF-IDF and provide information at the text structure level for evaluation.

[0070] In step S303, first extract the multidimensional vector, TF-IDF value, etc. of the academic paper to be evaluated and each academic paper in the data set according to the above method, represent each academic paper with a feature vector, and then calculate the distance between the academic paper to be evaluated and each academic paper in the data set using metrics such as Euclidean distance and cosine distance based on kNN. Select the nearest k academic papers as the nearest neighbors based on the distance, and calibrate the preliminary evaluation results using voting or weighted average method based on the scores of the nearest neighbor papers, wherein the scores of the nearest neighbor papers can be existing data marked when collecting the data set. Obtain the calibrated preliminary evaluation results.

[0071] In step S304, the preliminary evaluation results after XGBoost optimization, the supplementary information provided by TF-IDF and TextRank, and the preliminary evaluation results after kNN calibration are comprehensively considered from multiple dimensions such as the content quality, logical structure, and vocabulary usage of the paper. Through the preset scoring rules and evaluation templates, detailed evaluation content of the paper is generated, and an objective and comprehensive final score is given to complete the evaluation of the academic paper to be evaluated. In one embodiment, the preset scoring rules can set different weights for the evaluation indicators of different dimensions, and quantify the performance in each dimension. Then, a comprehensive evaluation of the academic paper to be evaluated is completed, and detailed evaluation content and objective final scores are provided to users, helping users understand the advantages and disadvantages of the paper, and providing a reference for the modification and improvement of the paper.

[0072] It can be seen that the intelligent evaluation method for academic papers based on multidimensional vector representation provided by this application utilizes multiple text vector representation technologies for multidimensional feature analysis, and combines multiple machine learning algorithms to comprehensively evaluate the quality of the papers, thereby improving the accuracy and efficiency of the evaluation.

[0073] Based on the same inventive concept, an embodiment of the present application also provides an intelligent evaluation device for academic papers based on multi-dimensional vector representation. Since the principle of solving the problem by the device in the embodiment of the present application is similar to the above-mentioned intelligent evaluation method for academic papers based on multi-dimensional vector representation in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0074] As the instruction manual Figure 4 As shown, an embodiment of the present application provides an intelligent evaluation device for academic papers based on multidimensional vector representation, the device comprising:

[0075] Extraction module 401 is used to extract multidimensional vectors from the academic paper to be evaluated; wherein the extracted multidimensional vectors include vocabulary vectors, part-of-speech vectors, and paragraph vectors;

[0076] A preliminary evaluation module 402 is configured to input the extracted vocabulary vectors, the part-of-speech vectors, and the paragraph vectors into a trained deep neural network model for processing to obtain a preliminary evaluation result of the academic paper to be evaluated;

[0077] The comprehensive evaluation module 403 is used to input the academic paper to be evaluated and the preliminary evaluation result into a comprehensive scoring model for processing to obtain the final evaluation result of the academic paper to be evaluated; wherein the comprehensive scoring model integrates multiple machine learning algorithms.

[0078] In one embodiment, the extraction module 401 performs multi-dimensional vector extraction on the academic paper to be evaluated, including: preprocessing the academic paper to be evaluated; the preprocessing includes denoising, word segmentation, part-of-speech tagging and paragraph segmentation; extracting vocabulary vectors from the preprocessed academic paper to be evaluated based on a word vector model; processing the vocabulary vectors and part-of-speech tagging information based on the part-of-speech vector model to obtain part-of-speech vectors; processing the vocabulary vectors, part-of-speech vectors and paragraph segmentation information based on the paragraph vector model to obtain paragraph vectors.

[0079] In one embodiment, the extracted multidimensional vector further includes document topic features, and the extraction module 401 processes the academic paper to be evaluated based on the LDA model to obtain the document topic features.

[0080] In one embodiment, the deep neural network model is a three-layer neural network model consisting of an input layer, a hidden layer, and an output layer, and the device further includes:

[0081] A training module is used to initialize the weights and biases of a deep neural network; forward propagate the training data to obtain prediction results; wherein the training data is a collection of vocabulary vectors, part-of-speech vectors, and paragraph vectors obtained by performing multidimensional vector extraction on a large number of collected academic paper samples; calculate the loss value based on the prediction results and the corresponding true labels; use the backpropagation algorithm to calculate the gradient value of the loss value with respect to the weights and biases, and adjust the weights and biases based on the gradient value until the deep neural network converges or reaches a preset number of training rounds.

[0082] In one embodiment, the comprehensive scoring model integrates multiple machine learning algorithms including XGBoost, TF-IDF, TextRank and kNN. The comprehensive evaluation module 403 inputs the academic paper to be evaluated and the preliminary evaluation result into the comprehensive scoring model for processing to obtain the final evaluation result of the academic paper to be evaluated, including: optimizing the preliminary evaluation result based on XGBoost to obtain an optimized preliminary evaluation result; inputting the academic paper to be evaluated into TF-IDF and TextRank for processing to obtain supplementary information; wherein, the vocabulary importance is calculated based on TF-IDF and the text structure is analyzed based on TextRank, and the obtained vocabulary importance and text structure information are used as the supplementary information; the preliminary evaluation result is calibrated based on kNN to obtain a calibrated preliminary evaluation result; the optimized preliminary evaluation result, the supplementary information and the calibrated preliminary evaluation result are comprehensively evaluated according to preset rules to obtain the final evaluation result of the academic paper to be evaluated.

[0083] In one embodiment, the comprehensive evaluation module 403 calibrates the preliminary evaluation result based on kNN to obtain the calibrated preliminary evaluation result, including: calculating the Euclidean distance between the academic paper to be evaluated and each academic paper in the data set based on kNN; selecting at least one academic paper with the closest Euclidean distance as the nearest neighbor academic paper; and calibrating the preliminary evaluation result according to the score of the nearest neighbor academic paper.

[0084] The present application provides an intelligent evaluation device for academic papers based on multidimensional vector representation, which extracts multidimensional vectors from the academic papers to be evaluated through an extraction module; wherein the extracted multidimensional vectors include vocabulary vectors, part-of-speech vectors and paragraph vectors; the extracted vocabulary vectors, part-of-speech vectors and paragraph vectors are input into a trained deep neural network model for processing through a preliminary evaluation module to obtain a preliminary evaluation result of the academic paper to be evaluated; the academic paper to be evaluated and the preliminary evaluation result are input into a comprehensive scoring model for processing through a comprehensive evaluation module to obtain a final evaluation result of the academic paper to be evaluated; wherein the comprehensive scoring model integrates multiple machine learning algorithms. Thus, a multidimensional feature analysis of the academic paper to be evaluated is performed, making the evaluation more in-depth, and a comprehensive evaluation of the paper quality is performed in combination with multiple machine learning algorithms, thereby improving the accuracy and efficiency of the evaluation.

[0085] Based on the same concept of the present invention, the specification Figure 5 As shown, an embodiment of the present application provides a structure of an electronic device 500, which includes: at least one processor 501, at least one network interface 504 or other user interface 503, a memory 505, and at least one communication bus 502. The communication bus 502 is used to achieve connection and communication between these components. The electronic device 500 optionally includes a user interface 503, including a display (for example, a touch screen, LCD, CRT, holographic imaging (Holographic) or projection (Projector), etc.), a keyboard or a pointing device (for example, a mouse, trackball (trackball), touchpad or touch screen, etc.).

[0086] The memory 505 may include a read-only memory and a random access memory, and provides instructions and data to the processor 501. A portion of the memory 505 may also include a non-volatile random access memory (NVRAM).

[0087] In some embodiments, the memory 505 stores the following elements, executable modules, or data structures, or a subset or extended set thereof:

[0088] Operating system 5051, including various system programs for implementing various basic services and processing hardware-based tasks;

[0089] The application module 5052 includes various application programs, such as a launcher, a media player, a browser, etc., which are used to implement various application services.

[0090] In an embodiment of the present application, by calling the program or instructions stored in the memory 505, the processor 501 is used to execute steps in a method for intelligent evaluation of academic papers based on multidimensional vector representation, which can realize multidimensional semantic analysis and improve evaluation efficiency and accuracy.

[0091] The present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps in the intelligent evaluation method for academic papers based on multi-dimensional vector representation are executed.

[0092] Specifically, the storage medium can be a general storage medium, such as a mobile disk, a hard disk, etc. When the computer program on the storage medium is run, it can execute the above-mentioned intelligent evaluation method for academic papers based on multi-dimensional vector representation.

[0093] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interface, the indirect coupling or communication connection of the device or unit can be electrical, mechanical or other forms.

[0094] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0095] In addition, each functional unit in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0096] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0097] Finally, it should be noted that the above embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The scope of protection of the present application is not limited thereto. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above embodiments within the technical scope disclosed in the present application, or replace some of the technical features therein with equivalents. However, these modifications, changes, or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application. They should all be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. An intelligent evaluation method for academic papers based on multidimensional vector representation, characterized by: The method comprises the following steps: Extract multidimensional vectors from the academic papers to be evaluated; the extracted multidimensional vectors include vocabulary vectors, part-of-speech vectors, and paragraph vectors; Inputting the extracted vocabulary vector, the part-of-speech vector, and the paragraph vector into a trained deep neural network model for processing to obtain a preliminary evaluation result of the academic paper to be evaluated; Inputting the academic paper to be evaluated and the preliminary evaluation result into a comprehensive scoring model for processing to obtain a final evaluation result of the academic paper to be evaluated; wherein the comprehensive scoring model integrates multiple machine learning algorithms, and the multiple machine learning algorithms integrated in the comprehensive scoring model include an extreme gradient boosting algorithm, a term frequency-inverse document frequency algorithm, a text ranking algorithm, and a k-nearest neighbor algorithm; inputting the academic paper to be evaluated and the preliminary evaluation result into the comprehensive scoring model for processing to obtain the final evaluation result of the academic paper to be evaluated includes the following steps: optimizing the preliminary evaluation result based on the extreme gradient boosting algorithm to obtain an optimized preliminary evaluation result; inputting the academic paper to be evaluated into the term frequency-inverse document frequency algorithm and the text ranking algorithm for processing to obtain supplementary information; wherein, calculating word importance based on the term frequency-inverse document frequency algorithm and analyzing text structure based on the text ranking algorithm, and using the obtained word importance and text structure information as the supplementary information; calibrating the preliminary evaluation result based on the k-nearest neighbor algorithm to obtain a calibrated preliminary evaluation result; and comprehensively evaluating the optimized preliminary evaluation result, the supplementary information, and the calibrated preliminary evaluation result according to preset rules to obtain the final evaluation result of the academic paper to be evaluated.

2. The intelligent evaluation method for academic papers based on multidimensional vector representation according to claim 1 is characterized in that: The multi-dimensional vector extraction of the academic paper to be evaluated includes the following steps: Preprocessing the academic papers to be evaluated; the preprocessing includes denoising, word segmentation, part-of-speech tagging, and paragraph segmentation; Extract vocabulary vectors from the pre-processed academic papers to be evaluated based on the word vector model; Process the vocabulary vector and part-of-speech tagging information based on the part-of-speech vector model to obtain the part-of-speech vector; Based on the paragraph vector model, the vocabulary vector, part-of-speech vector and paragraph segmentation information are processed to obtain the paragraph vector.

3. The intelligent evaluation method for academic papers based on multidimensional vector representation according to claim 2 is characterized in that: The extracted multidimensional vector also includes document topic features, wherein the document topic features are obtained by processing the academic paper to be evaluated based on a latent Dirichlet allocation model.

4. The intelligent evaluation method for academic papers based on multidimensional vector representation according to claim 1 is characterized in that: The deep neural network model is a three-layer neural network model consisting of an input layer, a hidden layer, and an output layer, and is trained as follows, including the following steps: Initialize the weights and biases of the deep neural network; Perform forward propagation on the training data to obtain prediction results; wherein the training data is a collection of vocabulary vectors, part-of-speech vectors, and paragraph vectors obtained by performing multidimensional vector extraction on a large number of collected academic paper samples; Calculate the loss value based on the predicted result and the corresponding true label; The backpropagation algorithm is used to calculate the gradient of the loss value with respect to the weight and bias, and the weight and bias are adjusted based on the gradient value until the deep neural network converges or reaches a preset number of training rounds.

5. The intelligent evaluation method for academic papers based on multidimensional vector representation according to claim 1 is characterized in that: The step of calibrating the preliminary evaluation result based on the k-nearest neighbor algorithm to obtain a calibrated preliminary evaluation result includes the following steps: Calculate the Euclidean distance between the academic paper to be evaluated and each academic paper in the dataset based on the k-nearest neighbor algorithm; Select at least one academic paper with the closest Euclidean distance as the nearest neighbor academic paper; The preliminary evaluation results are calibrated according to the scores of the nearest neighbor academic papers.

6. An intelligent evaluation device for academic papers based on multidimensional vector representation, characterized in that: The device comprises: An extraction module is used to extract multidimensional vectors from the academic papers to be evaluated; the extracted multidimensional vectors include vocabulary vectors, part-of-speech vectors, and paragraph vectors; A preliminary evaluation module is used to input the extracted vocabulary vectors, the part-of-speech vectors, and the paragraph vectors into a trained deep neural network model for processing to obtain a preliminary evaluation result of the academic paper to be evaluated; A comprehensive evaluation module is configured to input the academic paper to be evaluated and the preliminary evaluation result into a comprehensive scoring model for processing to obtain a final evaluation result of the academic paper to be evaluated; wherein the comprehensive scoring model integrates multiple machine learning algorithms, and the multiple machine learning algorithms integrated in the comprehensive scoring model include an extreme gradient boosting algorithm, a term frequency-inverse document frequency algorithm, a text ranking algorithm, and a k-nearest neighbor algorithm; inputting the academic paper to be evaluated and the preliminary evaluation result into the comprehensive scoring model for processing to obtain a final evaluation result of the academic paper to be evaluated, including: optimizing the preliminary evaluation result based on the extreme gradient boosting algorithm to obtain an optimized preliminary evaluation result; inputting the academic paper to be evaluated into a term frequency-inverse document frequency algorithm and a text ranking algorithm for processing to obtain supplementary information; wherein, calculating word importance based on the term frequency-inverse document frequency algorithm and analyzing text structure based on the text ranking algorithm, and using the obtained word importance and text structure information as the supplementary information; calibrating the preliminary evaluation result based on the k-nearest neighbor algorithm to obtain a calibrated preliminary evaluation result; and comprehensively evaluating the optimized preliminary evaluation result, the supplementary information, and the calibrated preliminary evaluation result according to preset rules to obtain the final evaluation result of the academic paper to be evaluated.

7. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the memory communicate via the bus. When the machine-readable instructions are executed by the processor, the steps of the intelligent evaluation method for academic papers based on multidimensional vector representation are performed as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, executes the steps of the intelligent evaluation method for academic papers based on multidimensional vector representation as described in any one of claims 1 to 5.

Images